End of training
Browse files
README.md
CHANGED
|
@@ -2,6 +2,8 @@
|
|
| 2 |
base_model: samzirbo/mT5.en-es.pretrained
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: mt5.balanced
|
| 7 |
results: []
|
|
@@ -13,6 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
# mt5.balanced
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [samzirbo/mT5.en-es.pretrained](https://huggingface.co/samzirbo/mT5.en-es.pretrained) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -40,6 +47,22 @@ The following hyperparameters were used during training:
|
|
| 40 |
- lr_scheduler_warmup_steps: 1000
|
| 41 |
- training_steps: 30000
|
| 42 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
### Framework versions
|
| 44 |
|
| 45 |
- Transformers 4.40.1
|
|
|
|
| 2 |
base_model: samzirbo/mT5.en-es.pretrained
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- bleu
|
| 7 |
model-index:
|
| 8 |
- name: mt5.balanced
|
| 9 |
results: []
|
|
|
|
| 15 |
# mt5.balanced
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [samzirbo/mT5.en-es.pretrained](https://huggingface.co/samzirbo/mT5.en-es.pretrained) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.4858
|
| 20 |
+
- Bleu: 39.6397
|
| 21 |
+
- Meteor: 0.6687
|
| 22 |
+
- Chrf++: 61.2886
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 47 |
- lr_scheduler_warmup_steps: 1000
|
| 48 |
- training_steps: 30000
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Chrf++ |
|
| 53 |
+
|:-------------:|:------:|:-----:|:---------------:|:-------:|:------:|:-------:|
|
| 54 |
+
| 4.0381 | 0.5398 | 3000 | 2.0786 | 30.3181 | 0.59 | 53.6607 |
|
| 55 |
+
| 2.3046 | 1.0795 | 6000 | 1.8303 | 34.3855 | 0.6263 | 57.2186 |
|
| 56 |
+
| 2.0531 | 1.6193 | 9000 | 1.6969 | 36.2615 | 0.643 | 58.7366 |
|
| 57 |
+
| 1.9175 | 2.1591 | 12000 | 1.6209 | 37.2847 | 0.6507 | 59.5299 |
|
| 58 |
+
| 1.814 | 2.6988 | 15000 | 1.5698 | 38.2556 | 0.6599 | 60.3273 |
|
| 59 |
+
| 1.746 | 3.2386 | 18000 | 1.5331 | 38.7361 | 0.6629 | 60.6706 |
|
| 60 |
+
| 1.6921 | 3.7783 | 21000 | 1.5058 | 39.1633 | 0.6658 | 60.9563 |
|
| 61 |
+
| 1.6484 | 4.3181 | 24000 | 1.4933 | 39.4633 | 0.6677 | 61.1991 |
|
| 62 |
+
| 1.6291 | 4.8579 | 27000 | 1.4869 | 39.5943 | 0.6687 | 61.2864 |
|
| 63 |
+
| 1.6185 | 5.3976 | 30000 | 1.4858 | 39.6397 | 0.6687 | 61.2886 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.40.1
|